用于业务流程模型后缀生成和剩余时间预测的编码器-解码器生成对抗网
Encoder-Decoder Generative Adversarial Nets for Suffix Generation and Remaining Time Prediction of Business Process Models
摘要：
本文提出了一种基于生成对抗网络（GANs）的编码器-解码器架构，该架构以端到端的方式生成活动序列及其时间戳。GANs可以很好地处理图像等可区分的数据。然而，后缀是一系列分类项。为此，我们使用Gumbel-Softmax分布来获得可微连续近似。训练的工作原理是在两个玩家的游戏中让一个神经网络对抗另一个（因此具有“对抗”性质），这导致生成接近地面事实的后缀。从实验评估中可以看出，该方法在预测后缀和相应剩余时间的准确性方面优于基线，尽管使用了朴素的特征编码，并且仅基于控制流和事件完成时间的工程特征。
英文摘要：
This paper proposes an encoder-decoder architecture grounded on Generative Adversarial Networks (GANs), that generates a sequence of activities and their timestamps in an end-to-end way. GANs work well with differentiable data such as images. However, a suffix is a sequence of categorical items. To this end, we use the Gumbel-Softmax distribution to get a differentiable continuous approximation. The training works by putting one neural network against the other in a two-player game (hence the "adversarial" nature), which leads to generating suffixes close to the ground truth. From the experimental evaluation it emerges that the approach is superior to the baselines in terms of the accuracy of the predicted suffixes and corresponding remaining times, despite using a naive feature encoding and only engineering features based on control flow and events completion time.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
